finewebedu-49K-embdnorm-seed336 / train_results.json
gartland's picture
Model save
86292f8 verified
raw
history blame contribute delete
253 Bytes
{
"epoch": 0.9999597601706168,
"total_flos": 7.388283196544123e+17,
"train_loss": 3.543048438910747,
"train_runtime": 65674.4502,
"train_samples": 3180839,
"train_samples_per_second": 48.433,
"train_steps_per_second": 0.189
}